Llama 2 7B Structural Prune 2.5x: benchmark results
Provider: Meta.
Aggregate Rating 1100 ± 43, rank #10721 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.23 | MC2 (%) (0-shot) | 33.8 |
| Open LLM Leaderboard v1 - MMLU | 25.58 | Accuracy (%) (5-shot) | 8.9 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
| Open LLM Leaderboard v1 - HellaSwag | 27.85 | Normalized accuracy (%) (10-shot) | 4.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 24.66 | Normalized accuracy (%) (25-shot) | 3.9 |
| Open LLM Leaderboard v1 - WinoGrande | 49.96 | Accuracy (%) (5-shot) | 2.7 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-structural-prune-2-5x · How It Works · Data refreshed daily, snapshot 2026-11-08.